English
Related papers

Related papers: No Clustering, No Routing: How Transformers Actual…

200 papers

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networks change after fine-tuning. In this work, we use centered…

Computation and Language · Computer Science 2021-09-21 Jason Phang , Haokun Liu , Samuel R. Bowman

Transformers, the backbone of modern large language models (LLMs), face inherent architectural limitations that impede their reasoning capabilities. Unlike recurrent networks, Transformers lack recurrent connections, confining them to…

Computation and Language · Computer Science 2024-10-30 Xiang Zhang , Juntai Cao , Chenyu You

Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the…

Machine Learning · Computer Science 2022-06-27 Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Cyril Zhang

Transformer-based Mixture-of-Experts (MoE) models have been driving several recent technological advancements in Natural Language Processing (NLP). These MoE models adopt a router mechanism to determine which experts to activate for routing…

Machine Learning · Computer Science 2024-09-11 Maryam Akhavan Aghdam , Hongpeng Jin , Yanzhao Wu

Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of encoder with attention that looks over the entire sequence and…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

Computation and Language · Computer Science 2023-10-31 Yangjun Wu , Kebin Fang , Dongxiang Zhang , Han Wang , Hao Zhang , Gang Chen

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing…

Machine Learning · Computer Science 2025-06-10 Wenhao Zhao , Qiushui Xu , Linjie Xu , Lei Song , Jinyu Wang , Chunlai Zhou , Jiang Bian

Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing. Hence, attention is being extensively studied to investigate various linguistic capabilities of Transformers,…

Computation and Language · Computer Science 2020-10-07 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

The self-attention mechanism has significantly advanced the field of natural language processing, facilitating the development of advanced language-learning machines. Although its utility is widely acknowledged, the precise mechanisms of…

Computation and Language · Computer Science 2026-02-04 Tal Halevi , Yarden Tzach , Ronit D. Gross , Shalom Rosner , Ido Kanter

Brain networks, graphical models such as those constructed from MRI, have been widely used in pathological prediction and analysis of brain functions. Within the complex brain system, differences in neuronal connection strengths parcellate…

Machine Learning · Computer Science 2023-05-09 Wei Dai , Hejie Cui , Xuan Kan , Ying Guo , Sanne van Rooij , Carl Yang

The attention mechanism is the primary component of the transformer architecture; it has led to significant advancements in deep learning spanning many domains and covering multiple tasks. In computer vision, the attention mechanism was…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Abdullah Nazhat Abdullah , Tarkan Aydin

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…

Language Models (LMs) recently incorporate mixture-of-experts layers consisting of a router and a collection of experts to scale up their parameter count given a fixed computational budget. Building on previous efforts indicating that…

Computation and Language · Computer Science 2024-09-24 Stefan Arnold , Marian Fietta , Dilara Yesilbas

Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that…

Machine Learning · Computer Science 2026-03-24 Tasmay Pankaj Tibrewal , Pritish Saha , Ankit Meda , Kunal Singh , Pradeep Moturi

Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their…

Computation and Language · Computer Science 2023-10-20 Shunjie Wang , Shane Steinert-Threlkeld

Owing to the use of attention mechanism to leverage the dependency across tokens, Transformers are efficient for natural language processing. By harnessing permutation properties broadly exist in resource allocation policies, each mapping…

Signal Processing · Electrical Eng. & Systems 2025-07-04 Jia Guo , Chenyang Yang
‹ Prev 1 3 4 5 6 7 10 Next ›